{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZNR26RGFF7XFA73GKE6RGBQNZK","short_pith_number":"pith:ZNR26RGF","schema_version":"1.0","canonical_sha256":"cb63af44c52fee507f66513d13060dcab6cf3a5cc2782a0ac32ce903b30424eb","source":{"kind":"arxiv","id":"2304.10513","version":3},"attestation_state":"computed","paper":{"title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jie Huang, Kevin Chen-Chuan Chang, Shen Zheng","submitted_at":"2023-04-20T17:48:43Z","abstract_excerpt":"Recent advancements in large language models, such as ChatGPT, have demonstrated significant potential to impact various aspects of human life. However, ChatGPT still faces challenges in providing reliable and accurate answers to user questions. To better understand the model's particular weaknesses in providing truthful answers, we embark an in-depth exploration of open-domain question answering. Specifically, we undertake a detailed examination of ChatGPT's failures, categorized into: comprehension, factuality, specificity, and inference. We further pinpoint factuality as the most contributi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.10513","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-20T17:48:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f9b88bab0e9d0450e2c65125773681e36b3458b0c80777b8fbd6168df4438c11","abstract_canon_sha256":"0b0b633062ba1bb5daf112438d35ddf8c8c8e694296269a7e4aa58abeea18aeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:44.539649Z","signature_b64":"bezVRWf0T7FghCiWgym5gHurlGKRElGADVq9yY18OXW0sIrRg6QQoIbbGwg2QF5rOy/Ea2IG8RYJK5mPivaNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb63af44c52fee507f66513d13060dcab6cf3a5cc2782a0ac32ce903b30424eb","last_reissued_at":"2026-07-05T07:19:44.539169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:44.539169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jie Huang, Kevin Chen-Chuan Chang, Shen Zheng","submitted_at":"2023-04-20T17:48:43Z","abstract_excerpt":"Recent advancements in large language models, such as ChatGPT, have demonstrated significant potential to impact various aspects of human life. However, ChatGPT still faces challenges in providing reliable and accurate answers to user questions. To better understand the model's particular weaknesses in providing truthful answers, we embark an in-depth exploration of open-domain question answering. Specifically, we undertake a detailed examination of ChatGPT's failures, categorized into: comprehension, factuality, specificity, and inference. We further pinpoint factuality as the most contributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10513","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.10513/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.10513","created_at":"2026-07-05T07:19:44.539218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10513v3","created_at":"2026-07-05T07:19:44.539218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10513","created_at":"2026-07-05T07:19:44.539218+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNR26RGFF7XF","created_at":"2026-07-05T07:19:44.539218+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNR26RGFF7XFA73G","created_at":"2026-07-05T07:19:44.539218+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNR26RGF","created_at":"2026-07-05T07:19:44.539218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.07521","citing_title":"Evaluating Hallucinations in Domain-Adapted Large Language Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00919","citing_title":"Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01798","citing_title":"Large Language Models Cannot Self-Correct Reasoning Yet","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12816","citing_title":"The role of System 1 and System 2 semantic memory structure in human and LLM biases","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK","json":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK.json","graph_json":"https://pith.science/api/pith-number/ZNR26RGFF7XFA73GKE6RGBQNZK/graph.json","events_json":"https://pith.science/api/pith-number/ZNR26RGFF7XFA73GKE6RGBQNZK/events.json","paper":"https://pith.science/paper/ZNR26RGF"},"agent_actions":{"view_html":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK","download_json":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK.json","view_paper":"https://pith.science/paper/ZNR26RGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10513&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNR26RGFF7XFA73GKE6RGBQNZK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNR26RGFF7XFA73GKE6RGBQNZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK/action/storage_attestation","attest_author":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK/action/author_attestation","sign_citation":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK/action/citation_signature","submit_replication":"https://pith.science/pith/ZNR26RGFF7XFA73GKE6RGBQNZK/action/replication_record"}},"created_at":"2026-07-05T07:19:44.539218+00:00","updated_at":"2026-07-05T07:19:44.539218+00:00"}